conference paper
Results on the Steepness in Backpropagation Neural Networks
Moerland, Perry
•
Thimm, Georg
•
Fiesler, Emile
Aguilar, Marc
1994
Proceedings of the '94 SIPAR-Workshop on Parallel and Distributed Computing
The backpropagation algorithm is widely used for training multilayer neural networks. In this publication the steepness of its activation functions is investigated. In specific, it is discussed that changing the steepness of the activation function is equivalent to changing the learning rate and the weights. Some applications of this result to optical and other hardware implementations of neural networks are given.
Type
conference paper
Author(s)
Moerland, Perry
Thimm, Georg
Fiesler, Emile
Editors
Aguilar, Marc
Date Issued
1994
Publisher place
Institute of Informatics, University P'erolles, Fribourg, Switzerland
Published in
Proceedings of the '94 SIPAR-Workshop on Parallel and Distributed Computing
Start page
91
End page
94
Subjects
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
Written at
EPFL
EPFL units
Available on Infoscience
March 10, 2006
Use this identifier to reference this record